AI Paper Atlas

Research map / Point clouds / Segmentation and detection

HPNet: Deep Primitive Segmentation Using Hybrid Representations

Siming Yan, Zhenpei Yang, Chongyang Ma, Haibin Huang, Etienne Vouga, Qixing Huang

ICCV 2021 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 71 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the descriptor module output (ablation)HPNet · ANSI / ABCPartsSeg-IoU: drop by 14.9% and 17.5%Improved
add the descriptor module output (ablation)HPNet · ANSI / ABCPartsType-IoU: drop by 6.5% and 13.4%Improved
add the smoothness module (ablation)HPNet · ANSI / ABCPartsSeg-IoU: 0.67% and 1.34% decrementsImproved
add the smoothness module (ablation)HPNet · ANSI / ABCPartsType-IoU: 0.17% and 1.13% decrementsImproved
add the consistency module (ablation)HPNet · ANSI / ABCPartsSeg-IoU: 1.31% and 1.69% decrementsImproved
add the consistency module (ablation)HPNet · ANSI / ABCPartsType-IoU: 0.37% and 2.18% decrementsImproved
learn combination weights instead of fixed (ablation)HPNet · ANSI / ABCPartsSeg-IoU: 0.08% and 0.46% decrementsImproved
learn combination weights instead of fixed (ablation)HPNet · ANSIType-IoU: 0.00% decrementsNo clear effect
combine both spectral descriptors (ablation)HPNet (p+n) · ANSISeg-IoU: 92.41 -> 94.15Improved
combine both spectral descriptors (ablation)HPNet (p+n) · ABCPartsSeg-IoU: 83.20 -> 85.24Improved
hybrid representations vs ParseNetHPNet (p+n) · ANSISeg-IoU: 88.57 -> 94.15Improved
hybrid representations vs ParseNetHPNet (p+n) · ABCPartsSeg-IoU: 82.14 -> 85.24Improved

Later papers that compared with this method

3 later accepted papers report HPNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy